Knowledge catalogue
arXiv:2603.19185v2 Announce Type: replace Abstract: Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative mo
arXiv:2602.06104v2 Announce Type: replace Abstract: Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task perfor
arXiv:2602.00616v3 Announce Type: replace Abstract: Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while prese
arXiv:2605.11186v1 Announce Type: new Abstract: Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and interm
arXiv:2510.09333v2 Announce Type: replace-cross Abstract: Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more relia
arXiv:2605.12325v1 Announce Type: new Abstract: Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial
arXiv:2605.08134v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity a
arXiv:2605.10556v1 Announce Type: new Abstract: As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly
arXiv:2605.08760v1 Announce Type: new Abstract: Federated Learning (FL) facilitates collaborative model training across decentralized clients while preserving data privacy by avoiding raw data exchang
arXiv:2605.08314v1 Announce Type: cross Abstract: SVD-based Low-rank compression reduces transformer parameters and nominal FLOPs, but these savings often translate poorly into real LLM serving speedu
arXiv:2602.22611v2 Announce Type: replace Abstract: In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties o
IBM Corp. subsidiary Red Hat today is unveiling a broad set of product and partnership announcements aimed at helping enterprises put artificial intelligence into operation, modernize infrastructure a
arXiv:2605.10285v1 Announce Type: cross Abstract: We present a theoretically grounded Gaussian process framework that leverages neural feature maps to construct expressive kernels. We show that the le
arXiv:2605.08114v1 Announce Type: new Abstract: We analyse three KV cache quantization schemes under a fair bit budget: extbf{KV} (scalar MSE baseline), extbf{KQV} (WHT + MSE on K; WHT + MSE + QJL on
arXiv:2605.08963v1 Announce Type: cross Abstract: Machine Learning (ML) models trained on complex health surveys such as the National Health and Nutrition Examination Survey (NHANES) often ignore prim
arXiv:2605.07557v1 Announce Type: new Abstract: Semi-supervised learning faces significant challenges in realistic scenarios where labeled data is scarce and unlabeled data follows unknown, arbitrary
This article discusses AWS infrastructure, tools, and services designed to support the training and deployment of large foundation models, enabling machine learning practitioners to leverage AWS's com
arXiv:2605.07162v1 Announce Type: new Abstract: Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However,
arXiv:2605.08003v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods
arXiv:2605.07639v1 Announce Type: new Abstract: Tacit knowledge plays a central role in human expertise, yet it remains difficult to capture, formalize, and reuse in machine-interpretable form. This c
arXiv:2605.07199v1 Announce Type: new Abstract: Marketing decisions reflect the interaction of latent consumer heterogeneity, time-varying internal states, and explicit interventions, a structure that
arXiv:2603.26498v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer interactions with text, images, an
Anthropic PBC today announced that it will use SpaceX Corp.’s Colossus 1 supercomputer to power its Claude chatbot. The system was originally built in 2024 by xAI Holdings Corp., an artificial intelli
arXiv:2410.09457v2 Announce Type: replace Abstract: Modern cryptographic methods for implementing privacy-preserving LLMs such as gls{HE} require the LLMs to have a polynomial form. Forming such a rep
arXiv:2605.03379v1 Announce Type: cross Abstract: Repeated sampling is a standard way to spend test-time compute, but its benefit is controlled by the latent distribution of correctness across example
arXiv:2605.00884v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficul
arXiv:2411.16821v5 Announce Type: replace Abstract: Non-autoregressive (NAR) language models offer notable efficiency in text generation by circumventing the sequential bottleneck of autoregressive de
arXiv:2509.10746v3 Announce Type: replace Abstract: Large language models in healthcare often produce emotionally flat or opaque responses, failing to provide the transparent reasoning required for cl
arXiv:2605.01910v1 Announce Type: new Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all n_k key and value vectors from KV cach
arXiv:2605.02072v1 Announce Type: new Abstract: Conformal prediction (CP) provides powerful, distribution-free prediction sets, but its guarantees rely on the exchangeability of training and test data
arXiv:2605.01416v1 Announce Type: cross Abstract: The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy
arXiv:2605.00528v1 Announce Type: cross Abstract: AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermedi
arXiv:2603.18413v3 Announce Type: replace-cross Abstract: A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating multiple analysis
Media and entertainment is undergoing a structural shift driven by fragmented audiences, new content formats and the growing role of AI in production workflows. The traditional broadcast model — built
arXiv:2604.27233v1 Announce Type: new Abstract: Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-ho
arXiv:2601.20239v4 Announce Type: replace Abstract: Fine-grained and contact-rich manipulation remain challenging for robots, largely due to the underutilization of tactile feedback. To address this,
arXiv:2411.18929v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through s
arXiv:2604.26820v1 Announce Type: new Abstract: Detectors often suffer from degraded performance, primarily due to the distributional gap between the source and target domains. This issue is especiall
arXiv:2604.26470v1 Announce Type: new Abstract: Industrial systems increasingly depend on Machine Learning (ML), and operate on heterogeneous nodes that must satisfy tight latency, energy, and memory
arXiv:2511.20714v2 Announce Type: replace-cross Abstract: World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic
arXiv:2601.06160v2 Announce Type: replace Abstract: Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produce
arXiv:2601.00545v3 Announce Type: replace Abstract: Many problems in robotics involve both continuous and discrete components, and modeling them together for estimation tasks has been a long standing
arXiv:2604.23271v1 Announce Type: new Abstract: Automated white blood cell (WBC) classification is essential for scalable leukaemia screening. However, real-world deployment is challenged by domain sh
arXiv:2511.20006v2 Announce Type: replace-cross Abstract: Automatic Pitch Correction (APC) enhances vocal recordings by aligning pitch deviations with intended musical notes. However, existing APC sys
arXiv:2512.10570v2 Announce Type: replace-cross Abstract: We propose a flexible deep neural network (DNN) framework for modeling survival data within a partially linear regression structure. The appro
arXiv:2604.23150v1 Announce Type: cross Abstract: Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportion
arXiv:2402.11789v5 Announce Type: replace-cross Abstract: Anomaly localization in images -- identifying regions that deviate from normal patterns -- is vital in applications such as medical diagnosis
arXiv:2604.22031v1 Announce Type: cross Abstract: We propose Mochi, a Graph Foundation Model that addresses task unification and training efficiency by adopting a meta-learning based training framewor
arXiv:2604.20913v1 Announce Type: new Abstract: Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. We
arXiv:2602.01493v2 Announce Type: replace-cross Abstract: Solving diverse partial differential equations (PDEs) is fundamental in science and engineering. Large language models (LLMs) have demonstrate
arXiv:2604.21172v1 Announce Type: cross Abstract: This paper develops a refined version of TAPO-description logic for the analysis of information behavior. The framework is treated not as a single hom
arXiv:2604.21197v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of l
arXiv:2604.20306v1 Announce Type: cross Abstract: Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However,
arXiv:2510.09574v2 Announce Type: replace Abstract: Autonomous navigation in unfamiliar environments requires robots to simultaneously explore, localise, and plan under uncertainty, without relying on
arXiv:2604.19943v1 Announce Type: new Abstract: Annotation pipelines in Natural Language Processing (NLP) commonly assume a single latent ground truth per instance and resolve disagreement through lab
arXiv:2604.20123v1 Announce Type: new Abstract: In natural images, object skeletons are used to represent geometric shapes. However, even slight variations in pose or movement can cause noticeable cha
arXiv:2604.20289v1 Announce Type: new Abstract: Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Rec
arXiv:2604.19530v1 Announce Type: new Abstract: Transformer-based scientific foundation models are increasingly deployed in high-stakes settings, but current architectures give deterministic outputs a
arXiv:2603.16091v2 Announce Type: replace-cross Abstract: In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet
arXiv:2604.19565v1 Announce Type: cross Abstract: Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods typically rely on gold-standard out